| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12099213551119177, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024198427102238356, | |
| "eval_loss": 13.663919448852539, | |
| "eval_runtime": 14.3749, | |
| "eval_samples_per_second": 12.104, | |
| "eval_steps_per_second": 6.052, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012099213551119177, | |
| "grad_norm": 9.261695861816406, | |
| "learning_rate": 5e-05, | |
| "loss": 13.384, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024198427102238355, | |
| "grad_norm": 14.41732120513916, | |
| "learning_rate": 0.0001, | |
| "loss": 11.4576, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.024198427102238355, | |
| "eval_loss": 8.201425552368164, | |
| "eval_runtime": 14.4387, | |
| "eval_samples_per_second": 12.051, | |
| "eval_steps_per_second": 6.025, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.036297640653357534, | |
| "grad_norm": 19.497350692749023, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.2957, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04839685420447671, | |
| "grad_norm": 0.022469736635684967, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5674, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04839685420447671, | |
| "eval_loss": 0.055541668087244034, | |
| "eval_runtime": 14.4806, | |
| "eval_samples_per_second": 12.016, | |
| "eval_steps_per_second": 6.008, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.060496067755595885, | |
| "grad_norm": 0.004296286031603813, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0006, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07259528130671507, | |
| "grad_norm": 0.0020078958477824926, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0001, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07259528130671507, | |
| "eval_loss": 9.67200321611017e-05, | |
| "eval_runtime": 14.5254, | |
| "eval_samples_per_second": 11.979, | |
| "eval_steps_per_second": 5.99, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08469449485783424, | |
| "grad_norm": 0.0024380383547395468, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09679370840895342, | |
| "grad_norm": 0.002887232694774866, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0001, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09679370840895342, | |
| "eval_loss": 5.233088813838549e-05, | |
| "eval_runtime": 14.6142, | |
| "eval_samples_per_second": 11.906, | |
| "eval_steps_per_second": 5.953, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1088929219600726, | |
| "grad_norm": 0.0019215194042772055, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12099213551119177, | |
| "grad_norm": 0.0021148412488400936, | |
| "learning_rate": 0.0, | |
| "loss": 0.0002, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12099213551119177, | |
| "eval_loss": 5.048857201472856e-05, | |
| "eval_runtime": 14.4828, | |
| "eval_samples_per_second": 12.014, | |
| "eval_steps_per_second": 6.007, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1513537444708352e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |